Single Domain Generalization with Model-aware Parametric Batch-wise Mixup

TL;DR

This paper introduces MPBM, a novel data augmentation method that uses model-aware, batch-wise mixup guided by adversarial queries to improve single domain generalization in machine learning models.

Contribution

The paper proposes a new augmentation technique, MPBM, combining adversarial queries and a parametric mixup generator with attention, enhancing model generalization across unseen domains.

Findings

Achieves state-of-the-art results on benchmark datasets.

Effectively enriches the training data with synthetic, informative instances.

Improves model robustness and adaptability in diverse environments.

Abstract

Single Domain Generalization (SDG) remains a formidable challenge in the field of machine learning, particularly when models are deployed in environments that differ significantly from their training domains. In this paper, we propose a novel data augmentation approach, named as Model-aware Parametric Batch-wise Mixup (MPBM), to tackle the challenge of SDG. MPBM deploys adversarial queries generated with stochastic gradient Langevin dynamics, and produces model-aware augmenting instances with a parametric batch-wise mixup generator network that is carefully designed through an innovative attention mechanism. By exploiting inter-feature correlations, the parameterized mixup generator introduces additional versatility in combining features across a batch of instances, thereby enhancing the capacity to generate highly adaptive and informative synthetic instances for specific queries. The synthetic data produced by this adaptable generator network, guided by informative queries, is expected to significantly enrich the representation space covered by the original training dataset and subsequently enhance the prediction model's generalizability across diverse and previously unseen domains. To prevent excessive deviation from the training data, we further incorporate a real-data alignment-based adversarial loss into the learning process of MPBM, regularizing any tendencies toward undesirable expansions. We conduct extensive experiments on several benchmark datasets. The empirical results demonstrate that by augmenting the training set with informative synthesis data, our proposed MPBM method achieves the state-of-the-art performance for single domain generalization.